Using Computer Vision and Depth Sensing to Measure Healthcare Worker-Patient Contacts and Personal Protective Equipment Adherence Within Hospital Rooms

Current issues in hand hygiene

BACKGROUND

Multiple aspects of hand hygiene have changed in recent years.

METHODS

A PubMed search was conducted to identify recent articles about hand hygiene.

RESULTS

The COVID-19 pandemic caused temporary changes in hand hygiene compliance rates and shortages of alcohol-based hand sanitizers (ABHSs), and in marketing of some products that were ineffective or unsafe. Fortunately, ABHSs are effective against SARS-CoV-2 and other emerging pathogens including Candida auris and mpox. Proper placement, maintenance, and design of ABHS dispensers have gained additional attention. Current evidence suggests that if an adequate volume of ABHS has been applied to hands, personnel must rub their hands together for at least 15 seconds before hands feel dry (dry time), which is the primary driver of antimicrobial efficacy. Accordingly, practical methods of monitoring hand hygiene technique are needed. Direct observation of hand hygiene compliance remains a challenge in many healthcare facilities, generating increased interest in automated hand hygiene monitoring systems (AHHMSs). However, several barriers have hindered widespread adoption of AHHMSs. AHHMSs must be implemented as part of a multimodal improvement program to successfully improve hand hygiene performance rates.

CONCLUSIONS

Remaining gaps in our understanding of hand hygiene warrant continued research into factors impacting hand hygiene practices.

Documentation of adherence to infection prevention best practice in patient records: a mixed-methods investigation

Background

Healthcare-associated infections remain a preventable cause of patient harm in healthcare. Full documentation of adherence to evidence-based best practices for each patient can support monitoring and promotion of infection prevention measures. Thus, we reviewed the extent, nature, and determinants of the documentation of infection prevention (IP) standards in patients with HAI.

Methods

We reviewed electronic patient records (EMRs) of patients included in four annual point-prevalence studies 2013–2016 who developed a device- or procedure-related HAI (surgical site infection (SSI), catheter-associated urinary tract infection (CAUTI), ventilator-associated infection (VAP), catheter-related bloodstream infection (CRBSI)). We examined the documentation quality of mandatory preventive measures published as institutional IP standards. Additionally, we undertook semi-structured interviews with healthcare providers and a two-step inductive (grounded theory) and deductive (Theory of Planned Behaviour) content analysis.

Results

Of overall 2972 surveyed patients, 249 (8.4%) patients developed 272 healthcare-associated infections. Of these, 116 patients met the inclusion criteria, classified as patients with SSI, CAUTI, VAP, CRBSI in 78 (67%), 21 (18%), 10 (9%), 7 (6%), cases, respectively. We found documentation of IP measures in EMRs in 432/1308 (33%) cases. Documentation of execution existed in the study patients’ EMRs for SSI, CAUTI, VAP, CRBSI, and overall, in 261/931 (28%), 27/104 (26%), 46/122 (38%), 26/151 (17%), and 360/1308 (28%) cases, respectively, and documentation of non-execution in 67/931 (7%), 2/104 (2%), 0/122 (0%), 3/151 (2%), and 72/1308 (6%) cases, respectively. Healthcare provider attitudes, subjective norms, and perceived behavioural control indicated reluctance to document IP standards.

Conclusions

EMRs rarely included conclusive data about adherence to IP standards. Documentation had to be established indirectly through data captured for other reasons. Mandatory institutional documentation protocols or technically automated documentation may be necessary to address such shortcomings in patient safety documentation.

Association between COVID-19 outcomes and mask mandates, adherence, and attitudes

We extend previous studies on the impact of masks on COVID-19 outcomes by investigating an unprecedented breadth and depth of health outcomes, geographical resolutions, types of mask mandates, early versus later waves and controlling for other government interventions, mobility testing rate and weather. We show that mask mandates are associated with a statistically significant decrease in new cases (-3.55 per 100K), deaths (-0.13 per 100K), and the proportion of hospital admissions (-2.38 percentage points) up to 40 days after the introduction of mask mandates both at the state and county level. These effects are large, corresponding to 14% of the highest recorded number of cases, 13% of deaths, and 7% of admission proportion. We also find that mask mandates are linked to a 23.4 percentage point increase in mask adherence in four diverse states. Given the recent lifting of mandates, we estimate that the ending of mask mandates in these states is associated with a decrease of -3.19 percentage points in mask adherence and 12 per 100K (13% of the highest recorded number) of daily new cases with no significant effect on hospitalizations and deaths. Lastly, using a large novel survey dataset of 847 thousand responses in 69 countries, we introduce the novel results that community mask adherence and community attitudes towards masks are associated with a reduction in COVID-19 cases and deaths. Our results have policy implications for reinforcing the need to maintain and encourage mask-wearing by the public, especially in light of some states starting to remove their mask mandates.

Automatic detection of hand hygiene using computer vision technology

OBJECTIVE

Hand hygiene is essential for preventing hospital-acquired infections but is difficult to accurately track. The gold-standard (human auditors) is insufficient for assessing true overall compliance. Computer vision technology has the ability to perform more accurate appraisals. Our primary objective was to evaluate if a computer vision algorithm could accurately observe hand hygiene dispenser use in images captured by depth sensors.

MATERIALS AND METHODS

Sixteen depth sensors were installed on one hospital unit. Images were collected continuously from March to August 2017. Utilizing a convolutional neural network, a machine learning algorithm was trained to detect hand hygiene dispenser use in the images. The algorithm's accuracy was then compared with simultaneous in-person observations of hand hygiene dispenser usage. Concordance rate between human observation and algorithm's assessment was calculated. Ground truth was established by blinded annotation of the entire image set. Sensitivity and specificity were calculated for both human and machine-level observation.

RESULTS

A concordance rate of 96.8% was observed between human and algorithm (kappa = 0.85). Concordance among the 3 independent auditors to establish ground truth was 95.4% (Fleiss's kappa = 0.87). Sensitivity and specificity of the machine learning algorithm were 92.1% and 98.3%, respectively. Human observations showed sensitivity and specificity of 85.2% and 99.4%, respectively.

CONCLUSIONS

A computer vision algorithm was equivalent to human observation in detecting hand hygiene dispenser use. Computer vision monitoring has the potential to provide a more complete appraisal of hand hygiene activity in hospitals than the current gold-standard given its ability for continuous coverage of a unit in space and time.

Ethical issues in using ambient intelligence in health-care settings

Ambient intelligence is increasingly finding applications in health-care settings, such as helping to ensure clinician and patient safety by monitoring staff compliance with clinical best practices or relieving staff of burdensome documentation tasks. Ambient intelligence involves using contactless sensors and contact-based wearable devices embedded in health-care settings to collect data (eg, imaging data of physical spaces, audio data, or body temperature), coupled with machine learning algorithms to efficiently and effectively interpret these data. Despite the promise of ambient intelligence to improve quality of care, the continuous collection of large amounts of sensor data in health-care settings presents ethical challenges, particularly in terms of privacy, data management, bias and fairness, and informed consent. Navigating these ethical issues is crucial not only for the success of individual uses, but for acceptance of the field as a whole.

Illuminating the dark spaces of healthcare with ambient intelligence

Advances in machine learning and contactless sensors have given rise to ambient intelligence-physical spaces that are sensitive and responsive to the presence of humans. Here we review how this technology could improve our understanding of the metaphorically dark, unobserved spaces of healthcare. In hospital spaces, early applications could soon enable more efficient clinical workflows and improved patient safety in intensive care units and operating rooms. In daily living spaces, ambient intelligence could prolong the independence of older individuals and improve the management of individuals with a chronic disease by understanding everyday behaviour. Similar to other technologies, transformation into clinical applications at scale must overcome challenges such as rigorous clinical validation, appropriate data privacy and model transparency. Thoughtful use of this technology would enable us to understand the complex interplay between the physical environment and health-critical human behaviours.

The 2016 Garrod Lecture: The role of the healthcare epidemiologist in antimicrobial chemotherapy-a view from the USA

Antimicrobial chemotherapy now spans 80 years and four generations. The healthcare epidemiologist has an important role to play in this field. Efforts focus in three areas: (i) minimizing the transmission of antimicrobial-resistant bacteria in healthcare settings (infection control); (ii) optimizing use of currently available antibacterial drugs (antibiotic stewardship); and (iii) recognizing and responding to opportunities for new drug development. For each area, the epidemiologist provides data that address four practical questions-'What is the problem?', 'What should be done?', 'Is it being done?' and 'Is it working?'. A team approach is crucial to acting on the epidemiological data. Examples are presented to illustrate different roles of the epidemiologist, and tools and measures that have been developed to address some problems of current importance. Monitoring of quality, integrity and security of data remains a major focus. The epidemiologist will continue to have a key role in antimicrobial chemotherapy.